Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# out
+
+This model is a pretrained version of the llava multimodal projector for [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the liuhaotian/LLaVA-Pretrain dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.002
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "square",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mm_hidden_size": 1024,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14",
+  "model_type": "llava_mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "tune_mm_mlp_adapter": true,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

configs/pretrain-llava-mistral.yml

@@ -0,0 +1,66 @@
+base_model: mistralai/Mistral-7B-v0.1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+# multimodal pretrain
+multimodal: true
+mm_vision_tower: openai/clip-vit-large-patch14
+tune_mm_mlp_adapter: true
+mm_freeze_backbone: true
+mm_vision_select_layer: -2
+mm_projector_type: mlp2x_gelu
+mm_image_folder: ./llava/
+mm_use_im_patch_token: false
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: ./data/blip_laion_cc_sbu_558k.json
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./out
+
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: true
+
+wandb_project: axolotl-llava
+wandb_entity: oaaic
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 64
+num_epochs: 1
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 0.002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+eval_steps:
+save_steps: 0.1
+debug:
+deepspeed: deepspeed/zero2.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<unk>"

mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899a57019694a451a762dd4a78adb8c8c8ff7c9d37fb2822f6cb927ef997d105
+size 41961085